CUDA Cores
VRAM
GB/s
6,912
CUDA Cores
1275
Base MHz
1410
Boost MHz
80GB HBM2e
5120-bit bus
40
FP32 TFLOPS
80
FP16 TFLOPS
400W
TDP
4
Available Instances
$1.01/hr
Starting Price
| Architecture | Ampere (Unknown) |
| Release Date | 2022-08-01 |
| Launch Price | $10,000.00 |
| Process | 7nm |
| Transistors | 54.2 Billion |
Gen 3
Tensor Cores
Disabled
Transformer Engine
Not Supported
Flash Attention
dual-slot
Form Factor
The NVIDIA A800 80GB was introduced in 2022 on the Ampere architecture. Its specification combines 6,912 CUDA cores and 432 Tensor Cores with 80GB of HBM2e, which defines both the workloads it can run and the batch sizes it can hold.
Based on its 80GB memory capacity, the A800 80GB is best evaluated for large-model training, high-batch inference, and memory-intensive scientific computing. Always size the model, optimizer state, KV cache, and framework overhead together rather than choosing a GPU from core count alone.
GPUvec currently tracks 4 cloud listings for the A800 80GB, with the lowest observed hourly rate at $1.01. Prices and availability can change by provider, region, and instance configuration, so verify the final rate before starting a workload.
For software planning, the A800 80GB combines 2,039 GB/s of memory bandwidth, CUDA compute capability the latest, and a 7nm manufacturing process. Confirm the minimum CUDA, PyTorch, TensorFlow, or driver version required by your application before renting or purchasing hardware.
Get started quickly with these trusted GPU cloud providers. We may earn a commission when you sign up.
Learn more about GPUs from these authoritative sources:
Official CUDA programming guide
NVIDIA GPU Specifications →Official NVIDIA GPU specs
TechPowerUp GPU Database →Comprehensive GPU specifications
CUDA Compute Capability Guide →GPU compute capability reference
The NVIDIA A800 80GB uses the Ampere architecture and combines 6,912 CUDA cores with 80GB of HBM2e. GPUvec records 2,039 GB/s memory bandwidth alongside architecture, release date, process node, accelerator features, and physical specifications so the page can be evaluated from source data instead of model-name assumptions.
GPUvec currently tracks 4 cloud listings, with an observed starting rate of $1.01 per hour. Provider rates can vary by region, host configuration, billing model, and availability. Use the provider directory and related-GPU links to compare an available alternative when this exact accelerator is not listed.
Start with the 80GB memory limit, then evaluate 2,039 GB/s memory bandwidth, compute features, and software compatibility for your workload. Model weights, KV cache, activations, optimizer state, and framework overhead all consume memory. Compare this page with related accelerators rather than assuming that a higher core count alone guarantees a better training or inference result.
| Category | Rank 1 | Rank 2 | Rank 3 |
|---|---|---|---|
| Best for Training | NVIDIA H200 | NVIDIA H100 | NVIDIA B200 |
| Best for Inference | NVIDIA A40 | NVIDIA A100 | NVIDIA A10 |
Compare GPU specifications and cloud instances to find the best GPU for your workload.